Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to academic studies and sources of evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements or findings from studies/sources

    np_acts-logits-general · gemini-2.0-flash

    findings and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.76
    ReusableCell
    -0.65
     resourceCulture
    -0.64
    principalTable
    -0.63
     myſelf
    -0.59
     himſelf
    -0.59
     ſever
    -0.57
    RenderAtEndOf
    -0.57
     olympiques
    -0.56
     femininos
    -0.56
    POSITIVE LOGITS
     say
    0.80
     indicate
    0.79
     tell
    0.70
     says
    0.62
     indicated
    0.60
     indicates
    0.60
     said
    0.59
     saying
    0.57
    indicate
    0.55
     tells
    0.55
    Act Density 0.676%

    No Known Activations